CN110147496B

Movatterモバイル変換

Info

Publication number: CN110147496B
Application number: CN201910392924.3A
Authority: CN
Inventors: 王学兵; 雷志海; 杜英豪; 熊超
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-05-13
Filing date: 2019-05-13
Publication date: 2021-06-25
Anticipated expiration: 2039-05-13
Also published as: CN110147496A

Abstract

The embodiment of the invention provides a content pushing method and a content pushing device, wherein the method comprises the following steps: pushing a task to be pushed according to a first pushing strategy; acquiring the attraction data volume of a first type of content to be pushed in a preset time length and acquiring the attraction data volume of a target content in the preset time length; when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content, acquiring a reference pushing characteristic corresponding to the target content; optimizing a push dimension corresponding to the first type of content to be pushed based on the reference push characteristic; and pushing the new task to be pushed according to a second pushing strategy. The content pushing method and device provided by the embodiment of the invention can help a platform to attract users.

Description

Content pushing method and device

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a content push method and apparatus.

Background

With the continuous development of internet technology and computer technology, on the basis that network information provides information to users from one side in the past, a form that users can independently create content and provide the content to other users for consumption is developed, and with the increase of the proportion of young users in network users, the latter form becomes a mainstream information sharing form gradually.

After a platform for mutual communication among users is created, the most important thing is to attract users to gather on the platform for communication and sharing. In the prior art, some contents which are generally interested are pushed to a user in order to attract the user platform, however, the content pushing mode of the existing platform is single, and the effect of attracting the user is not good.

Disclosure of Invention

The embodiment of the invention provides a content pushing method and device, and aims to solve the problems that the content pushing mode of the existing platform is single, and the effect of attracting users is poor.

In order to solve the technical problem, the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides a content pushing method, where the method includes:

pushing a task to be pushed according to a first pushing strategy, wherein the first pushing strategy comprises at least two pushing dimensions, the task to be pushed comprises at least two types of contents to be pushed, and each pushing dimension corresponds to each type of content to be pushed one by one;

acquiring the attraction data volume of a first type of content to be pushed in a preset time length and acquiring the attraction data volume of target content in the preset time length, wherein the target content is the content with the highest attraction data volume in the same type of content as the first type of content to be pushed;

when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content, acquiring a reference pushing characteristic corresponding to the target content;

optimizing a push dimension corresponding to the first type of content to be pushed based on the reference push characteristic;

and pushing a new task to be pushed according to a second pushing strategy, wherein the second pushing strategy comprises the optimized pushing dimensionality.

Optionally, the push dimension includes a first push parameter, where the first push parameter is a push time, a push channel, a push content format, or a push classification channel.

Optionally, when the reference push feature includes a second push parameter of the same type as the first push parameter, the step of optimizing a push dimension corresponding to the first type of content to be pushed based on the reference push feature includes:

and replacing the first push parameter in the push dimension corresponding to the first type of content to be pushed with the second push parameter to obtain the optimized push dimension.

Optionally, the step of pushing the new task to be pushed according to the second pushing policy includes:

extracting keywords from the target content;

screening out preferred push contents comprising the keywords from the new task to be pushed;

and pushing the corresponding preferred pushing content according to each pushing dimension.

Optionally, the first pushing policy includes a first pushing dimension, and the step of pushing the task to be pushed according to the first pushing policy includes:

and pushing a second analogical push content corresponding to the first push dimension in the task to be pushed according to the first push dimension.

Optionally, the first push policy further includes a push sub-policy, where the push sub-policy is at least one of an active sub-policy, an inactive sub-policy, a vertical sub-policy, or a keyword sub-policy.

Optionally, the step of pushing a type of pushed content corresponding to the first pushing dimension in the task to be pushed according to the first pushing dimension includes:

and pushing refined contents in a class of pushed contents corresponding to the first pushing dimension in the task to be pushed to a target user according to the first pushing dimension, wherein the target user is a user corresponding to the pushing sub-strategy, and the refined contents are contents corresponding to the pushing sub-strategy.

Optionally, the attraction data amount includes at least one of a browsing amount, a click amount, an approval amount, a sharing amount, a forwarding amount, a comment amount, and a resource data amount.

In a second aspect, an embodiment of the present invention further provides a content pushing apparatus, including:

the system comprises a pushing module, a pushing module and a pushing module, wherein the pushing module is used for pushing a task to be pushed according to a first pushing strategy, the first pushing strategy comprises at least two pushing dimensions, the task to be pushed comprises at least two types of contents to be pushed, and each pushing dimension corresponds to each type of content to be pushed one by one;

the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring the attraction data volume of a first type of content to be pushed in a preset time length and acquiring the attraction data volume of a target content in the preset time length, and the target content is the content with the highest attraction data volume in the same type of content as the first type of content to be pushed;

the second obtaining module is used for obtaining a reference pushing characteristic corresponding to the target content when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content;

an optimization module, configured to optimize a push dimension corresponding to the first type of content to be pushed based on the reference push characteristic;

the pushing module is further configured to push a new task to be pushed according to a second pushing strategy, where the second pushing strategy includes the optimized pushing dimension.

Optionally, the push dimension includes a first push parameter, where the first push parameter is push time, a push channel, a push content format, or a push classification channel.

Optionally, when the reference pushing feature includes a second pushing parameter of the same type as the first pushing parameter, the optimization module is further configured to replace the first pushing parameter in the pushing dimension corresponding to the first type of content to be pushed with the second pushing parameter, so as to obtain the optimized pushing dimension.

Optionally, the pushing module includes:

an extraction unit configured to extract a keyword from the target content;

the screening unit is used for screening out preferred push contents including the target content characteristics from the new task to be pushed;

and the pushing unit is used for pushing the optimized pushing dimensionality to the optimal pushing content corresponding to the optimized pushing dimensionality.

Optionally, the first pushing policy includes a first pushing dimension, and the pushing module is further configured to push, according to the first pushing dimension, a second analogized content corresponding to the first pushing dimension in the task to be pushed.

Optionally, the first push policy further includes a push sub-policy, where the push sub-policy is an active sub-policy, an inactive sub-policy, a vertical sub-policy, or a keyword sub-policy.

Optionally, the pushing module is further configured to push, according to the first pushing dimension, a refined content in a class of push contents corresponding to the first pushing dimension in the task to be pushed to a target user, where the target user is a user corresponding to the pushing sub-policy, and the refined content is a content corresponding to the pushing sub-policy.

In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a processor, a memory, and a computer program stored on the memory and executable on the processor, and when executed by the processor, the computer program implements the steps of the content push method described above.

In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements the steps of the content pushing method as described above.

In the embodiment of the invention, the task to be pushed is pushed through a first pushing strategy, then the reference pushing characteristic corresponding to the content with the highest attractive data amount in the same type of content to be pushed is obtained, the corresponding pushing dimension is optimized based on the reference pushing characteristic, and a new task to be pushed is pushed according to a second pushing strategy comprising the optimized pushing dimension. Therefore, the optimized pushing dimension can learn how to improve the attractive data volume of the content from the reference pushing characteristics, and the pushing effect of the new pushing task is improved, so that the new task to be pushed, which is pushed according to the second pushing strategy, is more attractive, and the user volume of the platform can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a flowchart of a content pushing method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of another content pushing method according to an embodiment of the present invention;

fig. 3 is an architecture diagram of a platform corresponding to the content push method in fig. 2;

fig. 4 is a schematic structural diagram of a content pushing apparatus according to an embodiment of the present invention;

fig. 5 is a structural diagram of another content push apparatus according to an embodiment of the present invention;

fig. 6 is a structural diagram of another content push device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a flowchart of a content push method according to an embodiment of the present invention, as shown in fig. 1, including the following steps:

step 101: pushing a task to be pushed according to a first pushing strategy, wherein the first pushing strategy comprises at least two pushing dimensions, the task to be pushed comprises at least two types of contents to be pushed, and each pushing dimension corresponds to each type of content to be pushed one by one.

In the embodiment of the invention, the task to be pushed is diversified content pushed by an operator of the platform for attracting a user to enter the platform and stay on the platform. The task to be pushed includes various types of contents to be pushed, and the types can be distinguished according to the attributes of the contents, wherein one piece of content may only belong to one type, or may belong to multiple types, for example: the results of the european finals can belong to the sports category as well as to the news category.

The first push strategy has a corresponding push dimension corresponding to each category of contents to be pushed, and each push dimension is used for pushing the corresponding category of contents to be pushed. The push dimension can push the content to be pushed to the user according to the characteristics of the content to be pushed so as to attract the user.

Each push dimension may be performed simultaneously and without interfering with each other, that is, when one push dimension pushes one type of content to be pushed corresponding to the push dimension, another push dimension may also push another type of content to be pushed corresponding to the push dimension.

The platform in the embodiment of the invention can be a network community and comprises at least one of forums, posts, bulletin boards, group discussions, personal knowledge publishing and personal spaces (personal centers). The platform can be operated in the form of a website or in the form of application software.

Step 102: the method comprises the steps of obtaining attraction data volume of a first type of content to be pushed in a preset time length, and obtaining attraction data volume of target content in the preset time length, wherein the target content is the content with the highest attraction data volume in the same type of content as the first type of content to be pushed.

In the embodiment of the invention, besides the content pushed by the operator, the user can also make the content by himself in the platform and push the content in the platform for consumption by other users, so that the content provided to the user on the platform not only comprises the content pushed by the platform operator, but also comprises the content made by many users himself.

The first type of content to be pushed may be any type of content to be pushed included in the task to be pushed. After the first type of content to be pushed is pushed for the preset time, the attraction data volume of the first type of content to be pushed in the preset time is obtained, meanwhile, the attraction data volume of other content of the same type as the first type of content to be pushed in the preset time is obtained, so that the attraction data volume of all the content of the type in the preset time is obtained, and further the target content of the type with the highest attraction data volume in the preset time can be determined. The target content may be content pushed by an operator or content pushed by a user.

The attraction data volume of the content is embodied by data representing the attraction of the content, and the higher the attraction data volume is, the higher the attraction of the content is, the more the user volume can be increased for the platform; a lower amount of appeal data indicates a lower content appeal, which may lead to difficulties in attracting users and even to a loss of platform user volume.

Step 103: and when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content, acquiring a reference pushing characteristic corresponding to the target content.

After the target content is determined in step 102, the attraction data amount of the first type of content to be pushed is compared with the attraction data amount of the target content.

When the attraction data volume of the first type of content to be pushed is equal to the attraction data volume of the target content, the first type of content to be pushed may be considered as the target content, or the first type of content to be pushed and the target content have the same attraction.

When the attraction data amount of the first type of content to be pushed is less than that of the target content, the first type of content to be pushed is considered to be not enough attractive for the target content. At this time, a reference push feature corresponding to the target content needs to be acquired, so that the push dimension learns how to attract the user by referring to the push feature.

When the target content is the content pushed by the operator, referring to the pushing characteristics as at least one pushing parameter in the pushing dimension corresponding to the target content; when the target content is the content pushed by the user, the reference pushing characteristic may be at least one of a pushing time, a pushing channel, a content form of pushing and a classification channel of pushing of the target content, since the content pushed by the user may be a random event and has no systematic algorithm support.

For example: the target content is a photo comment pushed by the user at 10 am and combined with pictures and texts, and the reference pushing characteristics can comprise at least one of pushing time at 10 am, a pushing content form combined with pictures and texts and a pushed movie channel; the target content is a live game pushed by the user in a bullet frame form, and the reference pushing feature may include at least one of a pushing channel for the bullet frame pushing, a pushing content form for the live game and a pushing game channel.

When the first type of content to be pushed includes a plurality of contents, the attraction data amount of the first type of content to be pushed, which is compared with the attraction data amount of the target content, may be the attraction data amount of the content having the highest attraction data amount among the plurality of contents, or may be an average value of the attraction data amounts of the plurality of contents, and is not limited thereto.

Step 104: optimizing a push dimension corresponding to the first type of content to be pushed based on the reference push characteristic.

After the push dimensionality corresponding to the first type of content to be pushed is optimized based on the reference push characteristic capable of attracting the user, the optimized push dimensionality also has the characteristic of attracting the user by referring to the push characteristic, and accordingly the subsequent attraction data volume of the first type of content to be pushed is improved.

Step 105: and pushing a new task to be pushed according to a second pushing strategy, wherein the second pushing strategy comprises the optimized pushing dimensionality.

The optimized pushing dimension can attract users better than the pushing dimension before optimization, so that the to-be-pushed task pushed by the second pushing strategy comprising the optimized pushing dimension can obtain higher attractive data volume than the to-be-pushed task pushed by the first pushing strategy comprising the pushing dimension before optimization, namely, the to-be-pushed task can attract users better, and therefore a platform for pushing a new to-be-pushed task by adopting the second pushing strategy can attract users better.

It should be noted that, compared to the first pushing policy, the second pushing policy may be that one pushing dimension is optimized and other pushing dimensions are not optimized, or that multiple pushing dimensions are optimized and other pushing dimensions are not optimized, or that all pushing dimensions are optimized, which is not limited herein.

In the embodiment of the invention, the task to be pushed is pushed through a first pushing strategy, then the reference pushing characteristic corresponding to the content with the highest attractive data volume in the same type of content to be pushed is obtained, the corresponding pushing dimension is optimized based on the reference pushing characteristic, and a new task to be pushed is pushed according to a second pushing strategy comprising the optimized pushing dimension. Therefore, the optimized pushing dimension can learn how to improve the attractive data volume of the content from the reference pushing characteristics, and the pushing effect of the new pushing task is improved, so that the new task to be pushed, which is pushed according to the second pushing strategy, is more attractive, and the user volume of the platform can be improved.

Referring to fig. 2, fig. 2 is a flowchart illustrating another content pushing method according to an embodiment of the present invention. In this embodiment, the push dimension includes a first push parameter, and the reference push feature includes a second push parameter of the same type as the first push parameter. The method is shown in fig. 2 and comprises the following steps:

step 201: pushing a task to be pushed according to a first pushing strategy, wherein the first pushing strategy comprises at least two pushing dimensions, the task to be pushed comprises at least two types of contents to be pushed, and each pushing dimension corresponds to each type of content to be pushed one by one.

The implementation process and beneficial effects of step 201 may be referred to the description in step 101, and are not described herein again.

As shown in fig. 3, the platform includes underlying resource data, including premium content and content floor resources. The high-quality content is the pushed task to be pushed. The task to be pushed can be high-quality content made by the operator, high-quality content submitted to the operator by the user to obtain payment, and high-quality content authorized to be promoted by the operator after the user pushes the platform.

The content form of the high-quality content can be characters, pictures, graphics and text combination, video, live broadcast and the like, and is not limited herein.

The content landing resources are resources used for pushing the tasks to be pushed in the platform and can comprise a plurality of waistcoat accounts and classification channels, the tasks to be pushed need to push various contents to be pushed in the platform through the plurality of waistcoat accounts, the phenomenon that the platform is quite hot is formed, and the function of attracting users is achieved. The classification channel is used for displaying the contents to be pushed belonging to the same class in one channel according to the classification of the tasks to be pushed, so that the purpose of displaying various contents to be pushed to a user is achieved. In addition, the content grounding resource can also comprise a personal center, namely, the content which is interested by the user is directly pushed to the personal center of the user.

In an optional implementation manner, the first push policy includes a first push dimension, and the step 201 may include:

As shown in fig. 3, the platform is provided with a plurality of push parameters to form a push dimension, a first push dimension may be formed by one or more of a push time, a push channel, a push content form and a push classification channel, and the platform can push a second analogy push content corresponding to the first push dimension to the platform to attract users.

The pushing time may be a pushing time point or a pushing time period when the platform pushes the second type of content to be pushed to the platform. The push times of different push dimensions are usually different according to the characteristics of the content to be pushed, for example: the hot news can be pushed in the morning, and the entertainment information can be pushed in the evening.

The push channel is a push mode in which the platform pushes the second type of content to be pushed to the platform user, and may be a mode in which the second type of content to be pushed is pushed in a content push area in which the user enters a home page of the platform, or a mode in which the user pushes the second type of content to be pushed to the user in a notification message when the user does not enter the platform, or a mode in which the user pushes the second type of content to be pushed to the user in a pop-up box when the user enters a channel related to the second type of content to be pushed in the platform, which is not limited herein.

The pushed content forms comprise forms of characters, pictures, image-text combination, audio, video, live broadcast and the like, and when the pushing dimensions comprise pushing time and the pushed content forms, the platform pushes the second type of content to be pushed according to the pushing dimensions, wherein the second type of content to be pushed in different content forms can be pushed to users at different pushing times.

The pushed classified channel may be understood as a classified channel corresponding to the second type of content to be pushed, which is pushed by the platform according to the pushing dimension. For example: the second type of content to be pushed is a game about a football world cup, and then the content to be pushed can be pushed to a sports channel or a football channel on the platform.

The categorized channels may also include a topic (IP) channel for displaying content associated with the topic exclusively within the channel, facilitating quick access to the topic channel. For example: during a football world cup game, a world cup channel is added on the platform for specially displaying the content related to the football world cup.

In this embodiment, the platform pushes the second analogized push content corresponding to the first push dimension in the task to be pushed according to the first push dimension, the platform pushes other analogized push contents corresponding to other push dimensions, and the multiple push dimensions cooperate with each other in a division manner, so that the platform can complete the push of the task to be pushed.

As shown in fig. 3, the platform is further provided with a push sub-policy to further optimize a push dimension composed of push parameters, where the push sub-policy is based on the push dimension and combines characteristics of a user to assist the push dimension in improving push accuracy.

The active sub-strategy is directed to an active user group in the platform for creating the content for consumption by other users, and the inactive sub-strategy is directed to an inactive user group for consuming the content. The ratio of active users to inactive users in the platform is about 2:8, with the active users and inactive users having different points of interest for the content. The push dimension is combined with the active sub-strategy and the inactive sub-strategy, so that the content to be pushed received by the active user can better accord with the interest of the active user, and the content to be pushed received by the inactive user can better accord with the interest of the inactive user.

Therefore, when the first pushing strategy further comprises the pushing sub-strategy, the pushing accuracy of the contents to be pushed of each pushing dimension can be further optimized, and the attraction of the platform to the user is further improved.

In another optional embodiment, in a case that the first push policy further includes the above push sub-policy, step 201 may be:

Taking the push sub-policy as the active sub-policy and the inactive sub-policy as examples: when the push dimension does not combine the active sub-strategy and the inactive sub-strategy, the push dimension sends a class of contents to be pushed corresponding to the push dimension to the active user and the inactive user; when the push dimension is combined with the active sub-strategy and the inactive sub-strategy, the push dimension pushes the content, which is interesting to the active user, in the corresponding class of contents to be pushed to the active user and pushes the content, which is interesting to the inactive user, in the corresponding class of contents to be pushed to the inactive user.

Likewise, the vertical sub-policy can distinguish users of different vertical classes, such as: the method comprises the following steps that a user A is only interested in the content of a National professional Basketball Association (NBA for short), a user B is only interested in the content of a Chinese professional Basketball Association (CBA for short), and when the content to be pushed is the content related to the Basketball, the pushing dimension can push all the content related to the Basketball to the user A and the user B when the pushing dimension is not combined with a vertical sub-strategy; when the push dimension is combined with the vertical sub-strategy, the push dimension can only push the content related to the NBA in the content related to the basketball to the user A, and push the content related to the CBA in the content related to the basketball to the user B.

The keyword sub-policy can also distinguish users with different keywords from a user group corresponding to the push dimension, and the mode is similar to the principle of the vertical sub-policy, and is not repeated here.

In this embodiment, the first push strategy is formed by the push dimensions and the push sub-strategies together, so that the push accuracy of the task to be pushed, pushed by the first push strategy, can be further optimized, and the attraction of the platform to the user is further improved.

It should be noted that the initial push dimension (i.e., the push dimension that has not been optimized) may be a combination of push parameters that is obtained by performing policy value calculation in advance based on each push parameter and each push sub-policy and has the highest policy value. Each push dimension may be a combination of the same push parameters or a combination of different push parameters.

Step 202: the method comprises the steps of obtaining attraction data volume of a first type of content to be pushed in a preset time length, and obtaining attraction data volume of target content in the preset time length, wherein the target content is the content with the highest attraction data volume in the same type of content as the first type of content to be pushed.

The attraction data volume may include at least one of a browsing volume, a click volume, an approval volume, a sharing volume, a forwarding volume, a comment volume, and a resource data volume. The resource data is a resource given by the user for the content, and the resource data may be money given by the user, or a virtual gift or virtual decoration purchased by the user on the platform, for example: the virtual gift can be used for gifting in a live broadcast, and money can also be used for rewarding the article.

The platform can determine the amount of resource data for each content from the various forms of resource data obtained for each content. The resource data amount of the content may be determined by the virtual gift that the content is given, virtual dress, and the number of money, for example: the sum of the gift acquisition times of the virtual gift, the virtual decoration acquisition times and the money acquisition times is used as the resource data amount; it is also possible to determine the resource data amount of the content by the value amounts of the virtual gift, virtual dress, and money, for example: when the money amount given by the content a is 5 pieces and the money amount given by the content B is 100 pieces, the resource data amount of the content B is 20 times of the resource data amount of the content a.

The platform can count and calculate the parameters included in the attraction data volume to obtain the attraction data volume of the content. For example: taking the click volume of the content as the attraction data volume of the content when the attraction data volume comprises the click volume; or, in the case that the attraction data amount includes the click amount and the like amount, the sum of the click amount and the like amount may be used as the attraction data amount, or the attraction data amount of the content may be calculated by combining the click amount and the like amount with a weight ratio, such as: and taking the sum of the product of the click volume and the first weight value and the product of the praise volume and the second weight value as the attraction data volume of the content. In other cases, the attraction data amount includes click amount and resource data amount, or includes praise amount and resource data amount, or includes share amount, forward amount, comment amount and resource data amount, etc., the calculation may be performed by referring to the above summation value or combining with the weight ratio, or may be performed in other manners, which is not limited herein.

Step 203: and when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content, acquiring a reference pushing characteristic corresponding to the target content.

The implementation process and beneficial effects of step 202 and step 203 may be referred to the description in steps 102 and 103, and are not described herein again.

Step 204: and replacing a first push parameter in a push dimension corresponding to the first type of content to be pushed with a second push parameter to obtain the optimized push dimension.

In this embodiment, the first push parameter may be a push time, a push channel, a push content format, or a push classification channel. Of course, in other embodiments of the present invention, multiple of the push time, the push channel, the pushed content format, or the pushed classified channel may also be used as the first push parameter.

When the first push parameter is a first push time corresponding to a first type of content to be pushed, and the reference push characteristic includes a second push time corresponding to a target content, step 204 may specifically be: and replacing the first pushing time corresponding to the first type of content to be pushed in the pushing dimension with the second pushing time to obtain the optimized pushing dimension.

In the case that the first push parameter is a first push channel corresponding to a first type of content to be pushed, and the reference push characteristic includes a second push channel corresponding to the target content, step 204 may specifically be: and replacing a first push channel corresponding to the first type of content to be pushed in the push dimension with a second push channel to obtain the optimized push dimension.

In the case that the first push parameter is a first content form corresponding to the first type of content to be pushed, and the reference push characteristic includes a second content form corresponding to the target content, step 204 may specifically be: and replacing a first content form corresponding to the first type of content to be pushed in the pushing dimension with a second content form to obtain the optimized pushing dimension.

In the case that the first push parameter is a first push classification channel corresponding to a first type of content to be pushed, and the reference push characteristic includes a second push classification channel corresponding to a target content, step 204 may specifically be: and replacing a first push classification channel corresponding to the first type of content to be pushed in the push dimensionality with a second push classification channel to obtain the optimized push dimensionality.

By replacing the first push parameter in the push dimension with the second push parameter in the reference push feature, the optimized push dimension can learn the feature of attracting the user, which is possessed by the reference push feature, so that the attraction data quantity of the content to be pushed, which is pushed by the optimized push dimension, is improved.

As shown in fig. 3, the attraction data volume of each type of content to be pushed is used as a basis for optimizing the pushing dimension, so that the optimized pushing dimension has the characteristic of attracting users, and the attraction data volume of the subsequently pushed content to be pushed is further increased.

Step 205: and pushing a new task to be pushed according to a second pushing strategy, wherein the second pushing strategy comprises the optimized pushing dimensionality.

The implementation process and the beneficial effect of step 205 may be referred to the description in step 105, and are not described herein again.

In an alternative embodiment, step 205 may include:

extracting keywords from the target content;

The target content may be considered as hot content that the user is interested in currently, the keyword is a representative word in the target content, and the keyword may be obtained by analyzing the target content by the platform, and the keyword may be a name (name, short name, nickname, etc.) of a party of the target content, or may be a subject, time, place, etc. of the target content. For example: when the target content is the related content of the off-track of a certain star, the keyword may include one or more of the name of the star, the name of the star partner, the "off-track" and the "small third".

After the keywords are determined, the preferred push content is screened out from the new task to be pushed, and the preferred push content comprises the keywords, namely the preferred push content is considered to be the content related to or similar to the target content, and is the content which can also attract the user to log in the platform for viewing.

Wherein, in the second push strategy, only part of the push dimensions may be optimized based on the reference push characteristics, and the other part may not be optimized. Whether the push dimension is optimized or not, each push dimension in the second push strategy is used for pushing the preferred push content in the corresponding content to be pushed.

As shown in fig. 3, the platform further uses the attraction data amount as a basis for optimizing the content to be pushed, and the platform pushes the corresponding preferred pushed content in each pushing dimension, so that the content attracting the user can be continuously pushed on the platform.

In the embodiment, the keywords of the target content can be extracted, the preferred push content including the keywords is screened out from the new content to be pushed, the attractive preferred push content is determined from the new content to be pushed, the preferred push content is pushed by using the push dimension, the attraction of the push content is improved, a user can be attracted to use the platform conveniently, and the user quantity of the platform is improved.

In this embodiment, when the reference push feature includes a second push parameter that is the same as the first push parameter in the push dimension, the first push parameter of the push dimension is replaced with the second push parameter, so that the optimized push dimension has a characteristic of increasing the attraction data amount of the content to be pushed, and further, the attraction of a new task to be pushed, which is pushed by the second push strategy including the optimized push dimension, is increased, and thus, the user amount of the platform can be increased.

Referring to fig. 4, fig. 4 is a structural diagram of a content pushing device according to an embodiment of the present invention, as shown in fig. 4, thecontent pushing device 400 includes a pushingmodule 401, a first obtainingmodule 402, a second obtainingmodule 403, and an optimizingmodule 404, where:

the pushingmodule 401 is configured to push a to-be-pushed task according to a first pushing policy, where the first pushing policy includes at least two pushing dimensions, the to-be-pushed task includes at least two types of to-be-pushed contents, and each pushing dimension corresponds to each type of to-be-pushed content one to one;

a first obtainingmodule 402, configured to obtain an attraction data amount of a first type of content to be pushed within a preset time period, and obtain an attraction data amount of a target content within the preset time period, where the target content is a content with a highest attraction data amount in the same type of content as the first type of content to be pushed;

a second obtainingmodule 403, configured to obtain a reference push feature corresponding to the target content when the attraction data amount of the first type of content to be pushed is smaller than the attraction data amount of the target content;

an optimizingmodule 404, configured to optimize, based on the reference push characteristic, a push dimension corresponding to the first type of content to be pushed;

the pushingmodule 401 is further configured to push a new task to be pushed according to a second pushing policy, where the second pushing policy includes the optimized pushing dimension.

Optionally, when the reference push feature includes a second push parameter of the same type as the first push parameter;

the optimizingmodule 404 is further configured to replace the first push parameter in the push dimension corresponding to the first type of content to be pushed with the second push parameter, so as to obtain the optimized push dimension.

Optionally, as shown in fig. 5, the pushingmodule 401 includes:

anextraction unit 4011, configured to extract a keyword from the target content;

thescreening unit 4012 is configured to screen out preferred push content including the target content feature from the new task to be pushed;

and the pushingunit 4013 is configured to push the preferred push content corresponding to the optimized push dimension.

Optionally, the first pushing policy includes a first pushing dimension, and the pushingmodule 401 is further configured to push, according to the first pushing dimension, a second analogized content corresponding to the first pushing dimension in the task to be pushed.

Optionally, the pushingmodule 401 is further configured to push, according to the first pushing dimension, a refined content in a class of pushing content corresponding to the first pushing dimension in the task to be pushed to a target user, where the target user is a user corresponding to the pushing sub-policy, and the refined content is a content corresponding to the pushing sub-policy.

Thecontent pushing apparatus 400 according to the embodiment of the present invention can implement each process implemented by the content pushing apparatus according to the method embodiments in fig. 1 to fig. 3, and for avoiding repetition, details are not described here again.

According to thecontent pushing device 400 provided by the embodiment of the invention, the optimized pushing dimension can learn how to improve the attraction data volume of the content from the reference pushing characteristics, so that the pushing effect of a new pushing task is improved, the new task to be pushed, which is pushed according to the second pushing strategy, is more attractive, and the user volume of the platform can be further improved.

Fig. 6 is a schematic hardware structure diagram of a content pushing apparatus for implementing various embodiments of the present invention.

Thecontent push device 600 includes but is not limited to: aradio frequency unit 601, anetwork module 602, anaudio output unit 603, aninput unit 604, asensor 605, adisplay unit 606, auser input unit 607, aninterface unit 608, amemory 609, aprocessor 610, and apower supply 611. Those skilled in the art will appreciate that the content push device configuration shown in fig. 6 does not constitute a limitation of the content push device, and that the content push device may include more or less components than those shown, or combine certain components, or a different arrangement of components. In the embodiment of the present invention, the content pushing device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.

Wherein theprocessor 610 is configured to: pushing a task to be pushed according to a first pushing strategy, wherein the first pushing strategy comprises at least two pushing dimensions, the task to be pushed comprises at least two types of contents to be pushed, and each pushing dimension corresponds to each type of content to be pushed one by one; acquiring the attraction data volume of a first type of content to be pushed in a preset time length and acquiring the attraction data volume of target content in the preset time length, wherein the target content is the content with the highest attraction data volume in the same type of content as the first type of content to be pushed; when the attraction data volume of the first type of content to be pushed is smaller than the attraction data volume of the target content, acquiring a reference pushing characteristic corresponding to the target content; optimizing a push dimension corresponding to the first type of content to be pushed based on the reference push characteristic; and pushing a new task to be pushed according to a second pushing strategy, wherein the second pushing strategy comprises the optimized pushing dimensionality.

Optionally, when the reference push feature includes a second push parameter of the same type as the first push parameter, theprocessor 610, when performing the step of optimizing the push dimension corresponding to the first type of content to be pushed based on the reference push feature, includes: and replacing the first push parameter in the push dimension corresponding to the first type of content to be pushed with the second push parameter to obtain the optimized push dimension.

Optionally, when the step of pushing the new task to be pushed according to the second pushing policy is executed by theprocessor 610, the step includes: extracting keywords from the target content; screening out preferred push contents comprising the keywords from the new task to be pushed; and pushing the corresponding preferred pushing content according to each pushing dimension.

Optionally, the first pushing policy includes a first pushing dimension, and when the step of pushing the task to be pushed according to the first pushing policy is executed by theprocessor 610, the step includes: and pushing a second analogical push content corresponding to the first push dimension in the task to be pushed according to the first push dimension.

Optionally, when the step of pushing a type of pushed content corresponding to the first pushing dimension in the task to be pushed according to the first pushing dimension is executed by theprocessor 610, the step includes: and pushing refined contents in a class of pushed contents corresponding to the first pushing dimension in the task to be pushed to a target user according to the first pushing dimension, wherein the target user is a user corresponding to the pushing sub-strategy, and the refined contents are contents corresponding to the pushing sub-strategy.

Thecontent push apparatus 600 can implement the processes implemented by the content push apparatus in the foregoing embodiments, and in order to avoid repetition, the details are not described here.

According to thecontent pushing device 600 of the embodiment of the invention, the optimized pushing dimension can learn how to improve the attraction data volume of the content from the reference pushing characteristics, so that the pushing effect of a new pushing task is improved, the new task to be pushed, which is pushed according to the second pushing strategy, is more attractive, and the user volume of the platform can be further improved.

It should be understood that, in the embodiment of the present invention, theradio frequency unit 601 may be used for receiving and sending signals during a message sending and receiving process or a call process, and specifically, receives downlink data from a base station and then processes the received downlink data to theprocessor 610; in addition, the uplink data is transmitted to the base station. In general,radio frequency unit 601 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. Further, theradio frequency unit 601 may also communicate with a network and other devices through a wireless communication system.

The content push device provides wireless broadband internet access to the user through thenetwork module 602, such as helping the user send and receive e-mails, browse webpages, access streaming media, and the like.

Theaudio output unit 603 may convert audio data received by theradio frequency unit 601 or thenetwork module 602 or stored in thememory 609 into an audio signal and output as sound. Also, theaudio output unit 603 may also provide audio output related to a specific function performed by the content push apparatus 600 (e.g., a call signal reception sound, a message reception sound, etc.). Theaudio output unit 603 includes a speaker, a buzzer, a receiver, and the like.

Theinput unit 604 is used to receive audio or video signals. Theinput Unit 604 may include a Graphics Processing Unit (GPU) 6041 and amicrophone 6042, and theGraphics processor 6041 processes image data of a still picture or video obtained by an image capturing apparatus (such as a camera) in a video capture mode or an image capture mode. The processed image frames may be displayed on thedisplay unit 606. The image frames processed by thegraphic processor 6041 may be stored in the memory 609 (or other storage medium) or transmitted via theradio frequency unit 601 or thenetwork module 602. Themicrophone 6042 can receive sound, and can process such sound into audio data. The processed audio data may be converted into a format output transmittable to a mobile communication base station via theradio frequency unit 601 in case of the phone call mode.

Thecontent push device 600 further includes at least onesensor 605, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor that can adjust the brightness of thedisplay panel 6061 according to the brightness of ambient light, and a proximity sensor that can turn off thedisplay panel 6061 and/or the backlight when thecontent pushing apparatus 600 is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when stationary, and can be used to identify the posture of the content push device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), and vibration identification related functions (such as pedometer, tapping); thesensors 605 may also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which are not described in detail herein.

Thedisplay unit 606 is used to display information input by the user or information provided to the user. TheDisplay unit 606 may include aDisplay panel 6061, and theDisplay panel 6061 may be configured by a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

Theuser input unit 607 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the content push apparatus. Specifically, theuser input unit 607 includes atouch panel 6071 andother input devices 6072.Touch panel 6071, also referred to as a touch screen, may collect touch operations by a user on or near it (e.g., operations by a user on or neartouch panel 6071 using a finger, stylus, or any suitable object or accessory). Thetouch panel 6071 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to theprocessor 610, receives a command from theprocessor 610, and executes the command. In addition, thetouch panel 6071 can be implemented by various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. Theuser input unit 607 may includeother input devices 6072 in addition to thetouch panel 6071. Specifically, theother input devices 6072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a track ball, a mouse, and a joystick, which are not described herein again.

Further, thetouch panel 6071 can be overlaid on thedisplay panel 6061, and when thetouch panel 6071 detects a touch operation on or near thetouch panel 6071, the touch operation is transmitted to theprocessor 610 to determine the type of the touch event, and then theprocessor 610 provides a corresponding visual output on thedisplay panel 6061 according to the type of the touch event. Although in fig. 6, thetouch panel 6071 and thedisplay panel 6061 are two independent components to implement the input and output functions of the content push apparatus, in some embodiments, thetouch panel 6071 and thedisplay panel 6061 may be integrated to implement the input and output functions of the content push apparatus, and are not limited herein.

Theinterface unit 608 is an interface for connecting an external device to thecontent push apparatus 600. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input/output (I/O) port, a video I/O port, an earphone port, and the like. Theinterface unit 608 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within thecontent push device 600 or may be used to transmit data between thecontent push device 600 and an external device.

Thememory 609 may be used to store software programs as well as various data. Thememory 609 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, thememory 609 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

Theprocessor 610 is a control center of the content push apparatus, connects various parts of the entire content push apparatus using various interfaces and lines, and performs various functions of the content push apparatus and processes data by running or executing software programs and/or modules stored in thememory 609 and calling data stored in thememory 609, thereby performing overall monitoring of the content push apparatus.Processor 610 may include one or more processing units; preferably, theprocessor 610 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into theprocessor 610.

Thecontent pushing device 600 may further include a power supply 611 (such as a battery) for supplying power to each component, and preferably, thepower supply 611 may be logically connected to theprocessor 610 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system.

In addition, thecontent pushing apparatus 600 includes some functional modules that are not shown, and are not described herein again.

Preferably, an embodiment of the present invention further provides a content pushing apparatus, including aprocessor 610, amemory 609, and a computer program stored in thememory 609 and capable of running on theprocessor 610, where the computer program, when executed by theprocessor 610, implements each process of the content pushing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the foregoing content push method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.

While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A method for pushing content, the method comprising:

2. The method of claim 1, wherein the push dimension comprises a first push parameter, and wherein the first push parameter is a push time, a push channel, a pushed content format, or a pushed category channel.

3. The method according to claim 2, wherein when the reference push characteristic includes a second push parameter of the same type as the first push parameter, the step of optimizing the push dimension corresponding to the first type of content to be pushed based on the reference push characteristic includes:

4. The method according to claim 1, wherein the step of pushing the new task to be pushed according to the second pushing policy comprises:

extracting keywords from the target content;

5. The method of claim 1, wherein the first pushing policy comprises a first pushing dimension, and wherein the step of pushing the task to be pushed according to the first pushing policy comprises:

6. The method of claim 5, wherein the first push policy further comprises a push sub-policy, and wherein the push sub-policy is at least one of an active sub-policy, an inactive sub-policy, a vertical sub-policy, or a keyword sub-policy.

7. The method according to claim 6, wherein the step of pushing a type of push content corresponding to a first push dimension in the task to be pushed according to the first push dimension includes:

8. The method of claim 1, wherein the attraction data volume comprises at least one of a browsing volume, a click volume, an approval volume, a sharing volume, a forwarding volume, a comment volume, and a resource data volume;

the resource data amount is determined by the number of times of the virtual gift, the virtual dress and the money which are given by the content, or the resource data amount is determined by the value amount of the virtual gift, the virtual dress and the money which are given by the content.

9. A content pushing apparatus, comprising:

10. The content pushing apparatus according to claim 9, wherein the pushing dimension includes a first pushing parameter, and the first pushing parameter is a pushing time, a pushing channel, a pushed content form, or a pushed category channel.

11. The content pushing device of claim 10, wherein when the reference push characteristic includes a second push parameter of the same type as the first push parameter,

the optimization module is further configured to replace the first push parameter in the push dimension corresponding to the first type of content to be pushed with the second push parameter, so as to obtain the optimized push dimension.

12. The content pushing apparatus according to claim 9, wherein the pushing module comprises:

an extraction unit configured to extract a keyword from the target content;

13. The content pushing device of claim 9, wherein the first pushing policy comprises a first pushing dimension,

the pushing module is further configured to push, according to the first pushing dimension, second analogized pushing content corresponding to the first pushing dimension in the task to be pushed.

14. The content pushing apparatus according to claim 13, wherein the first pushing policy further comprises a pushing sub-policy, and the pushing sub-policy is an active sub-policy, an inactive sub-policy, a vertical sub-policy, or a keyword sub-policy.

15. The content pushing apparatus according to claim 14, wherein the pushing module is further configured to push, according to the first pushing dimension, refined content in a class of pushed content corresponding to the first pushing dimension in the task to be pushed to a target user, where the target user is a user corresponding to the pushing sub-policy, and the refined content is content corresponding to the pushing sub-policy.

16. The content pushing apparatus according to claim 9, wherein the attraction data amount includes at least one of a browsing amount, a click amount, an approval amount, a sharing amount, a forwarding amount, a review amount, and a resource data amount;

17. An electronic device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the content push method according to any one of claims 1 to 8.

18. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the content push method according to any one of claims 1 to 8.